Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4052 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8387. Min Range: -1.8387

Max Act: 1.8387. Min Act: -0.0000

Data Index: 853973 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 1.8387. Min Range: -1.8387

Max Act: 1.6063. Min Act: -0.0000

Data Index: 687760 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 1.8387. Min Range: -1.8387

Max Act: 1.6515. Min Act: -0.0000

Data Index: 1587251 (Python Code)

Max Activating Token Index: 1005

Text #3

Max Range: 1.8387. Min Range: -1.8387

Max Act: 1.5236. Min Act: -0.0000

Data Index: 1063437 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 1.8387. Min Range: -1.8387

Max Act: 1.3883. Min Act: -0.0000

Data Index: 1370734 (Python Code)

Max Activating Token Index: 881

Text #5

Max Range: 1.8387. Min Range: -1.8387

Max Act: 1.3147. Min Act: -0.0000

Data Index: 769892 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 1.8387. Min Range: -1.8387

Max Act: 1.3665. Min Act: -0.0000

Data Index: 42707 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 1.8387. Min Range: -1.8387

Max Act: 1.3671. Min Act: -0.0000

Data Index: 1496234 (Python Code)

Max Activating Token Index: 751

Text #8

Max Range: 1.8387. Min Range: -1.8387

Max Act: 1.3640. Min Act: -0.0000

Data Index: 1521385 (Python Code)

Max Activating Token Index: 456

Text #9

Max Range: 1.8387. Min Range: -1.8387

Max Act: 1.3500. Min Act: -0.0000

Data Index: 1618653 (Python Code)

Max Activating Token Index: 824

Text #10

Max Range: 1.8387. Min Range: -1.8387

Max Act: 1.3353. Min Act: -0.0000

Data Index: 473993 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 1.8387. Min Range: -1.8387

Max Act: 1.2444. Min Act: -0.0000

Data Index: 944224 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 1.8387. Min Range: -1.8387

Max Act: 1.3150. Min Act: -0.0000

Data Index: 1378649 (Python Code)

Max Activating Token Index: 577

Text #13

Max Range: 1.8387. Min Range: -1.8387

Max Act: 1.1822. Min Act: -0.0000

Data Index: 563968 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 1.8387. Min Range: -1.8387

Max Act: 1.2208. Min Act: -0.0000

Data Index: 508770 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 1.8387. Min Range: -1.8387

Max Act: 1.2620. Min Act: -0.0000

Data Index: 745617 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 1.8387. Min Range: -1.8387

Max Act: 1.2180. Min Act: -0.0000

Data Index: 1442142 (Python Code)

Max Activating Token Index: 984

Text #17

Max Range: 1.8387. Min Range: -1.8387

Max Act: 1.1766. Min Act: -0.0000

Data Index: 815346 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 1.8387. Min Range: -1.8387

Max Act: 1.2523. Min Act: -0.0000

Data Index: 1386423 (Python Code)

Max Activating Token Index: 730

Text #19

Max Range: 1.8387. Min Range: -1.8387

Max Act: 1.2871. Min Act: -0.0000

Data Index: 1372457 (Python Code)

Max Activating Token Index: 163